We introduce the task of human action anomaly detection (HAAD), which aims to identify anomalous motions in an unsupervised manner given only the pre-determined normal category of training action samples. Compared to prior human-related anomaly detection tasks which primarily focus on unusual events from videos, HAAD involves the learning of specific action labels to recognize semantically anomalous human behaviors. To address this task, we propose a normalizing flow (NF)-based detection framework where the sample likelihood is effectively leveraged to indicate anomalies. As action anomalies often occur in some specific body parts, in addition to the full-body action feature learning, we incorporate extra encoding streams into our framework for finer modeling of body subsets. Our framework is thus multi-level to jointly discover global and local motion anomalies. Furthermore, to show awareness of the potentially jittery data during recording, we resort to discrete cosine transformation by converting the action samples from the temporal to the frequency domain to mitigate the issue of data instability. Extensive experimental results on two human action datasets demonstrate that our method outperforms the baselines formed by adapting state-of-the-art human activity AD approaches to our task of HAAD.

Zoning search strategies have been utilized to solve multimodal multi-objective optimization problems (MMOPs). However, effectively transferring knowledge among subspaces and mitigating the negative transfer remain significant challenges. To this end, we propose an adaptive transfer learning-assisted zoning search (ZSATL) method to assist other multimodal multi-objective evolutionary algorithms (MMOEAs) in obtaining more equivalent Pareto optimal solutions and a high-quality Pareto front approximation. In the ZSATL, the zoning search is employed to segment the search space into many subspaces. Moreover, an adaptive transfer learning method is proposed to alleviate the negative transfer issue. If the distribution of solution sets in two subspaces is similar, the transfer learning method is employed to exchange knowledge. Otherwise, the brain storm optimization algorithm is employed to find promising regions for mining useful knowledge. The performance of the proposed algorithm is compared with that of seven advanced MMOEAs on balanced and imbalanced MMOPs. Based on the experimental results, the ZSATL can locate more equivalent Pareto optimal solutions in the decision space and find a better PF approximation when compared with other competitors.

Large-scale global optimization (LSGO) presents significant challenges due to the high dimensionality and complexity of the search space. We propose an IGKT (Inter-Generational Knowledge Transfer) optimization method incorporating a novel knowledge transfer mechanism to address these challenges. The proposed mechanism enables the algorithm to reduce reliance on stochastic exploration and enhance convergence efficiency by transferring information from the best-performing individuals across generations, guiding the population toward promising regions in the search space. Experimental results on the CEC2013 LSGO benchmark suite demonstrate that IGKT outperforms several state-of-the-art algorithms across various tested functions, achieving superior convergence speed and solution quality. Additionally, the IGKT framework handles both separable and non-separable functions and tasks, including those with overlapping and highly coupled variables. In summary, IGKT represents a powerful tool for addressing complex, high-dimensional optimization problems, providing a robust and adaptable solution for LSGO.

Competitive swarm optimizer (CSO) is an efficient and effective swarm intelligence approach, especially for large-scale optimization. This paper presents an enhanced version of CSO termed improved CSO with linear population reduction (L-ICSO). The novel triple-individuals competitive mechanism is introduced to strengthen the optimization performance of L-ICSO, and the linear population reduction mechanism from L-SHADE is integrated into L-ICSO to highlight the explorative search in the initial phase of optimization and emphasize the exploitative behavior in the late phase. We conduct comprehensive numerical experiments in 100-dimensional CEC2017 benchmark functions. Ten state-of-the-art optimizers such as L-SHADE, jSO, L-SHADE-cnEpSin, and the original CSO are employed as competitor algorithms. The Mann–Whitney U and Holm multiple comparison tests are used to measure the statistical significance between L-ICSO and competitor algorithms. The experimental results and statistical analysis confirm the efficiency and effectiveness of our proposed L-ICSO in addressing large-scale optimization problems. The source code of L-ICSO can be found at https://github.com/RuiZhong961230/L-ICSO.

Dataset distillation (DD) condenses large datasets into compact yet informative substitutes, preserving performance comparable to the original dataset while reducing storage, transmission costs, and computational consumption. However, previous DD methods mainly focus on distilling information from images, often overlooking the semantic information inherent in the data. The disregard for context hinders the model's generalization ability, particularly in tasks involving complex datasets, which may result in illogical outputs or the omission of critical objects. In this study, we integrate vision-language methods into DD by introducing text prototypes to distill language information and collaboratively synthesize data with image prototypes, thereby enhancing dataset distillation performance. Notably, the text prototypes utilized in this study are derived from descriptive text information generated by an open-source large language model. This framework demonstrates broad applicability across datasets without pre-existing text descriptions, expanding the potential of dataset distillation beyond traditional image-based approaches. Compared to other methods, the proposed approach generates logically coherent images containing target objects, achieving state-of-the-art validation performance and demonstrating robust generalization. Source code and generated data are available in https://github.com/zou-yawen/Dataset-Distillation-via-Vision-Language-Category-Prototype/

Black-Box unsupervised domain adaptation (BBUDA) learns knowledge only with the prediction of target data from the source model without access to the source data and source model, which attempts to alleviate concerns about the privacy and security of data. However, incorrect pseudo-labels are prevalent in the prediction generated by the source model due to the cross-domain discrepancy, which may substantially degrade the performance of the target model. To address this problem, we propose a novel approach that incrementally selects high-confidence pseudo-labels to improve the generalization ability of the target model. Specifically, we first generate pseudo-labels using a source model and train a crude target model by a vanilla BBUDA method. Second, we iteratively select high-confidence data from the low-confidence data pool by thresholding the softmax probabilities, prototype labels, and intra-class similarity. Then, we iteratively train a stronger target network based on the crude target model to correct the wrongly labeled samples to improve the accuracy of the pseudo-label. Experimental results demonstrate that the proposed method achieves state-of-the-art black-box unsupervised domain adaptation performance on three benchmark datasets.

With the continuous expansion of the city scale and urbanization, urban road networks are becoming increasingly complex. Moreover, severe and extreme weather events, earthquakes, and other natural disasters occur frequently. Therefore, how to effectively and quickly evacuate urban crowd in dynamic environments is an urgent issue. To carry out the above objective, an unmanned system-guided crowd evacuation method is proposed in the current study. In the proposed method, the robot can perceive the environment in a timely and accurate manner to generate the evacuation map via advanced information technologies such as the Internet of Things or urban brain. Subsequently, an improved elliptic tangent graph approach based on global and local information (ETG-GLI) is utilized to plan a feasible and short evacuation path in large-scale scenarios. Finally, a novel crowd evacuation model based on the social force model is proposed to simulate the actual crowd evacuation process in complex and large-scale environments. To test the performance of the proposed path planning method, 25 different scenarios are proposed to simulate complex urban crowd evacuation environments. The experimental results show that the proposed algorithm outperforms other competitors in terms of path planning ability and computational time. Three actual evacuation cases with 324 pedestrians are modeled to further test the performance of the proposed algorithm. The simulation results demonstrate that the unmanned system-guided crowd evacuation method can find a shorter evacuation path for reducing the evacuation time in three complex and large-scale environments when compared with three other methods. Therefore, the proposed algorithm is a highly effective and promising approach to provide useful decision support and guidance for actual urban planning and urban emergence management.Note to Practitioners—In modern cities, the population density is high and the road network is complex. To evacuate the crowd in a timely and safe manner, planning feasible and short paths in large-scale and complex environments is a critical and challenging task. Therefore, the present study aims to provide a novel method to plan high-quality evacuation routes to guide the pedestrian flow. The performance of the proposed approach is validated in 25 test scenarios and 3 real-world instances. Experimental results demonstrate that the proposed algorithm performs well in terms of path length and computation time. Moreover, the proposed crowd evacuation model can simulate the actual process of crowd evacuation.

The task of incomplete multi-view clustering (IMvC) aims to partition multi-view data with a lack of completeness into different clusters. The incompleteness can be typically categorized into the case of instance-missing and view-unaligned MvC. However, prior methods either consider each of them or struggle to pursue consistent latent representations among views. In this paper, we propose two forms of contrastive learning paradigms to jointly handle both cases for IMvC. Specifically, we design an instance-oriented contrastive (IOC) learning strategy to achieve intra-class consistency. As negative samples within different datasets can exhibit diverse distributions, we formulate a parameterized boundary for IOC learning to flexibly deal with such differing data modes. To preserve inter-view consistency, we further devise category-oriented contrastive (COC) learning such that data from different views can be seamlessly integrated into a combined semantic space. We also recover the missing instances with the learned latent representations in a reconstructing manner for realigning the incomplete multi-view data to facilitate clustering. Our approach unifies the solution to both incomplete cases into one formulation. To demonstrate the effectiveness of our model, we conduct four types of MvC tasks on six benchmark multi-view datasets and compare our method against state-of the-art IMvC methods. Extensive experiments show that our method achieves state-of-the-art performance, quantitatively and qualitatively.

Black-box unsupervised domain adaptation (BBUDA) is a challenging task that transfers knowledge from the source domain to the target domain without access to the source data and source model, thus alleviating public concerns about data security. However, BBUDA requires the source model to function as a black-box predictor for the target data, and the pseudo-labels often exhibit class imbalance, which degrades the performance. To tackle this problem, we propose employing the synthetic minority oversampling technique (SMOTE) and adaptive sampling to rebalance data. Given that predictions often contain errors, we first select reliable high-confidence data before using SMOTE to generate synthetic samples for the minority class. Second, we incrementally select high-confidence data from the remaining low-confidence data with an adaptive sampling rate for each class, in which the minority class (with the fewest samples) is assigned a higher sampling rate and the majority class (with the most samples) is assigned a lower sampling rate. The experimental results demonstrate that our method can mitigate the class imbalance and further improve the performance of the target model.

The fast gradient signed method (FGSM) is an efficient white-box attack method that uses the gradient information to generate adversarial examples. However, applying the classic FGSM to real-world applications is often difficult due to the challenge of obtaining the internal structure of the models. Therefore, we have made slight modifications to the conventional genetic algorithm (GA) to effectively optimize the gradient signed function of the classic FGSM and generate adversarial examples from the perspective of the black-box attack. To attack multiple given target classes simultaneously, we initialize multiple different subpopulations and ensure that each subpopulation attacks a specified target class. Additionally, we propose two different strategies to migrate successfully attacked subpopulations into unsuccessful ones to ramp up attacks on unsuccessful classes. To evaluate the performance of the proposed algorithm, we compare it with the conventional GA when attacking the well-trained VGG19_BN model on the CIFAR-10 database. Furthermore, we investigate the impact of the proposed strategies on performance and analyze their respective contributions. The experimental results confirm that the proposed algorithm can successfully attack a greater variety of classes at a faster rate.

We propose an adaptive scouting strategy which is a refinement of our previous work to further improve the performance of the fireworks algorithm (FWA). The proposed strategy makes full use of the currently obtained fitness landscape information to avoid inefficient searches. Specifically, we introduce two new modifications to our previously proposed scouting strategy to more quickly adjust the balance between exploration and exploitation in the face of various optimization scenarios. The first modification is that the initial explosion center migrates with better generated spark individual instead of being fixed on initial firework individual, i.e., the next round of the initial explosion center will move to the recently generated spark individual when the current tracing direction has no potential. The other is to actively reduce the explosion amplitude of subsequent explosion operation when a potential spark individual is generated. Otherwise, increase the explosion amplitude to escape from the trapped local area quickly. To evaluate the performance of the new proposed strategy, we designed a series of comparative experiments and used 28 functions from the CEC 2013 test suite as the benchmark. The experimental results confirmed that the adaptive scouting strategy shows better performance and faster convergence speed especially for complex multimodal optimization problems.